© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 420
    Prev
    Next
    INDEX
    Explanations

    cultural context, technical terms, abbreviations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    แบบ
    1.49
    óri
    1.41
    Static
    1.39
    ધન
    1.35
     ملف
    1.34
    ยาว
    1.34
    。
    1.31
     في
    1.30
    يث
    1.29
    マイ
    1.28
    POSITIVE LOGITS
     hinder
    1.72
     patriarchal
    1.63
     stigmat
    1.62
     intrig
    1.61
     uncomfortable
    1.57
     seamen
    1.54
     disadvantaged
    1.51
     inflamed
    1.51
     contingent
    1.51
     epile
    1.50
    Activations Density 0.000%

    No Known Activations